Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Teruo Kunihiro
What It Means to Use a Fly’s Neural Wiring
You can use a fruit fly's neural connectivity data as the structure of a neural network. When I saw demos of fly-inspired models on social media, my first reaction was: “Flies are pretty impressive.” But what does using their wiring actually involve? This article starts with a tiny model built from measured connections, then looks at a Rubik's Cube implementation and my Sudoku experiment.
Jev HighwayEnv: 60 Seconds Without a Crash
“I'll send Jev the cars' positions and speeds and have it choose whether to change lanes or slow down. How hard can that be?” That was the idea. Instead, the car crashed almost immediately. When I added braking, it stopped and stayed there. When I added acceleration, it crashed again. This is the story of getting it to drive for 60 seconds—roughly 1.20 km—without a collision, on a three-lane highway with traffic approaching from behind.
Trying Out AgentInspect
Imagine a travel agent answering: Tokyo is rainy today. Choose indoor sightseeing. Did it check the weather first? Or did it return that sentence without calling the weather tool? The final answer looks the same, but the execution paths are different. Checking that path matters. If a prompt should trigger a particular tool and the tool never runs, something has gone wrong before we even judge the answer. Seeing that failure helps identify where the application needs fixing.
Linking Go pprof Samples to OpenTelemetry Traces with OTLP Profiles
Traces tell us which request was slow. CPU profiles tell us which functions consumed CPU time. Can we start from a slow span and open only the CPU profile samples captured while that span was running?
I Built EnvVault to Keep API Keys Out of .env Files
I still use .env files in local development. They are simple, they work with almost every framework, and they are easy to understand: OPENAI_API_KEY=sk-... DATABASE_URL=postgres://... But as I started using coding agents more often, plaintext secrets in project directories started to bother me. Giving an agent access to a repository is not exactly the same as giving another person access to your working directory, but it is close enough to make me more careful.
Project Docs over SSH for AI Agents
I have been thinking about where to put design notes and implementation plans generated by AI agents. I often use Superpowers-style planning and docs workflows: before implementing something, I write down the spec and implementation direction in an SDD-like document. That workflow is useful, but I do not really like keeping every generated document in the repository forever. Code has builds and tests, so breakage is easier to see. Old design notes and implementation plans are different.
How I Make Claude Code's 5-Hour Usage Window Last Longer on Claude Pro
When using Claude Code with Claude Pro, one problem you will almost certainly run into is the Usage Limit. The actual usage depends on many things: message length, attached files, conversation history, the model you are using, and the features you enable. Claude Pro has a session-based limit that resets every five hours, as well as a weekly usage limit. (Claude Help Center) I use Claude Pro with the assumption that I will eventually hit the limit.
Choosing Models for an Agentic Chat App on Amazon Bedrock
When building an agentic chat application on Amazon Bedrock, one of the first hard decisions is model selection. This article is not a rigorous benchmark or formal evaluation. It is simply a set of practical notes from experimenting with multiple Bedrock models while building a personal agentic chat application. Pricing, supported features, and regional behavior change frequently, so you should always validate with official documentation and your own workload before making production decisions.
TanStack Was Not the Whole Story: Mini Shai-Hulud Was an npm/PyPI Supply-Chain Worm
This article is based on public reporting available as of 2026-05-13. Mini Shai-Hulud is still an actively tracked campaign, so affected packages and IOCs (indicators of compromise) may change. In May 2026, a supply-chain compromise was reported across TanStack's npm packages. Malicious versions were published for 42 @tanstack/* packages, and installing those versions triggered a credential stealer. If you look only at TanStack, the incident can seem like a single npm compromise.
Building a Home Personal Assistant with Claude Managed Agents
Introduction Claude Managed Agents was just announced, so I tried using it to build a personal assistant for household tasks. What I wanted was pretty simple: an AI I can call from Slack that can handle family notes, tasks, reminders, and schedules without too much ceremony. Things like birthdays, what gifts I bought last year, school handouts, grocery co-op deadlines, and small day-to-day household tasks. My first impression was very positive.
Semver in Retrograde
This is a submission for the DEV April Fools Challenge What I built I built a dependency analysis tool that delivers executive-grade reports about your project's emotional state. It just happens to be astrology. So I built Semver in Retrograde. You paste a package.json, click "Analyze my dependency aura", and get a straight-faced executive report about the project's emotional state.
Lessons from the Spring 2026 OSS Incidents: Hardening npm, pnpm, and GitHub Actions Against Supply-Chain Attacks
March 2026 saw a rapid succession of OSS supply-chain incidents. In Trivy, an attacker repointed 76 of the 77 version tags for trivy-action and 7 tags for setup-trivy to a malicious commit, and a tampered v0.69.4 binary was released. In LiteLLM, malicious 1.82.7 and 1.82.8 packages were uploaded to PyPI, and the maintainers later identified 1.83.0 as the clean release.
What I Learned from Reading Claude Code’s Reconstructed Source
What I Learned from Reading Claude Code’s Reconstructed Source Around March 31, 2026, it became widely known that parts of Claude Code CLI’s implementation could be reconstructed from source maps that had remained in the npm package. A public mirror circulated for a while, but it was not an official open-source release by Anthropic, and it has since turned into a different project.
Code Review with AIs
Hello folks. Have you ever wanted to quickly run code reviews using multiple AIs? I have. If you really want to do something like this, you can have an AI generate a script and run it locally right away. Problem solved! …But if we stop there, the blog post ends immediately, so please stick with me for a little longer. The problem I want to solve In most cases, that really does solve it—but scripts created this way often end up calling pay-as-you-go APIs such as the ChatGPT API.
ai-docs managing AI generated context files
When developing alongside AI agents, one of the first headaches that arises is how to manage the flood of context files they generate. The Problem Here are a few specific challenges I kept facing: As your AI coding assistant evolves, you naturally want to externalize and back up its memory files. These files are not deterministic and will inevitably differ across local environments and each developer's. Git merges often lead to nasty conflicts. During code review, these files just get in the way.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Teruo
Contact Teruo, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack